End of training

README.md

@@ -21,12 +21,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.2320
-- Accuracy: 0.1180
-- Precision: 0.5651
-- Recall: 0.3145
-- F1: 0.4041
-- Hamming Loss: 0.1988
+- Loss: 1.3691
+- Accuracy: 0.1133
+- Precision: 0.5836
+- Recall: 0.2698
+- F1: 0.3690
+- Hamming Loss: 0.2017
 
 ## Model description
 
@@ -53,7 +53,6 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: constant
 - lr_scheduler_warmup_ratio: 0.05
 - num_epochs: 10
-- mixed_precision_training: Native AMP
 
 ### Training results
 

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbb4aef2207b837cf1dc3290f0e8c2583a344845e5574f6a5f25937c024c93ca
+oid sha256:26ca211e7e7a8ce9ab5cefad6cb43c2386d6013cc41cb0c0bd9e507937540ada
 size 9920584

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c93341424be23697c167aeb0bb48b6685e23e737cefd2ae9086414d7c0c6f316
+oid sha256:bddb109ad694e5827992bd7f9eaf1f4d45c7bfcb6410d9cc25cf765516b81a4d
 size 4920